Methods and systems for compressing video content are presented. The methods and systems include analyzing a sequence of media frames stored in the memory device and calculating a displacement level of each of the media frames. The displacement level indicates how different each of the media frames is to a previous media frame. The sequence of media frames is divided into a plurality of cuts where each cut ends at a media frame having a substantially high displacement level. Frames to be removed from the sequence of media frames are identified in each cut based upon the frame's displacement level. The identified frames are then removed.

An electronic device includes an image sensor including a first pixel subset with a first sensitivity and a second pixel subset having with a second sensitivity, and a processor to process image data generated through the image sensor. The processor obtains image data through each of the first pixel subset and the second pixel subset, select at least one sub-image data based at least on the attribute information of the first sub-image data and the second sub-image data of the image data, and obtain focus information corresponding to the external subject using the selected sub-image data.

In one aspect, an example method includes (i) determining a blur delta that quantifies a difference between a level of blurriness of a first frame of a video and a level of blurriness of a second frame of the video, wherein the second frame is subsequent to and adjacent to the first frame; (ii) determining a contrast delta that quantifies a difference between a contrast of the first frame and a contrast of the second frame; (iii) determining a fingerprint distance between a first image fingerprint of the first frame and a second image fingerprint of the second frame; (iv) determining a keyframe score using the blur delta, the contrast delta, and the fingerprint distance; (v) based on the keyframe score, determining that the second frame is a keyframe; and (vi) outputting data indicating that the second frame is a keyframe.

In one aspect, an example method includes (i) extracting a sequence of audio features from a portion of a sequence of media content; (ii) extracting a sequence of video features from the portion of the sequence of media content; (iii) providing the sequence of audio features and the sequence of video features as an input to a transition detector neural network that is configured to classify whether or not a given input includes a transition between different content segments; (iv) obtaining from the transition detector neural network classification data corresponding to the input; (v) determining that the classification data is indicative of a transition between different content segments; and (vi) based on determining that the classification data is indicative of a transition between different content segments, outputting transition data indicating that the portion of the sequence of media content includes a transition between different content segments.

In one aspect, an example method includes (i) determining, by a playback device, a loudness level of first media content that the playback device is receiving from a first source; (ii) comparing, by the playback device, the determined loudness level of the first media content with a reference loudness level indicated by a loudness level profile for the first media content; (iii) determining, by the playback device, a target volume level for the playback device based on a difference between the determined loudness level of the first media content and the reference loudness level; and (iv) while the playback device presents second media content from a second source in place of the first media content, adjusting, by the playback device, a volume of the playback device toward the target volume level.

A method for implementing a soft data association modeled with probabilities is provided. The association probabilities are computed in an intertwined expectation maximization (EM) scheme with an optical flow computation that maximizes the expectation (marginalization) over all associations. In addition, longer tracks can be enabled by computing the affine deformation with respect to the initial point and using the resulting residual as a measure of persistence. The computed optical flow enables a varying temporal integration that is different for every feature and sized inversely proportional to the length of the optical flow. The results can be seen in egomotion and very fast vehicle sequences.

The disclosure relates to a method of processing a sequence of image frames to reduce its length. One implementation may involve extracting coefficients (e.g., Discrete Cosine Transform coefficients) from components of individual frames, and comparing the resulting coefficients for sequential frames to identify frames having the least change from a prior frame. Also, scene change values for each frame may be calculated and placed in a sorted list to facilitate identification of frames for removal. Frame removal may be conducted in rounds, where a group of pictures (GOP) may only have one frame removed for any given round.

Methods and apparatus to detect commercial advertisements associated with media presentations are disclosed. An example method involves receiving a video frame and detecting a change in box-formatting between the video frame and a subsequent video frame. A transition between the video frame and the subsequent video frame is indicated as a commercial advertisement transition based on the detected change in box-formatting.

The present disclosure provides a system and method for generating a video synopsis. The method may include obtaining a video captured by a movable camera at a plurality of positions, the video including a sequence of video frames; determining, for each of at least part of the sequence of video frames, a position label of the video frame that indicates one of the plurality of positions of the movable camera; classifying the at least part of the sequence of video frames into a plurality of groups based on their position labels; determining one or more objects of interest in at least one of the plurality of groups; generating, for the at least one of the plurality of groups, a video synopsis based on the one or more objects of interest.

A data processing device includes: a digital signal processor; at least one processor; and at least one memory device configured to store a plurality of instructions, which when executed by the at least one processor, cause the at least one processor to operate to: output a first determination result relating to a scene of content through use of sound data; select processing for the sound data by a first selection method based on the first determination result; determine an attribute of the content from among a plurality of attribute candidates; and select the processing by a second selection method, which is different from the first selection method, based on a determination result of the attribute, wherein the digital signal processor is configured to execute the processing selected by the at least one processor on the sound data.